joey00072 / nanoGRPOLinks
nanoGRPO is a lightweight implementation of Group Relative Policy Optimization (GRPO)
☆116Updated 3 months ago
Alternatives and similar repositories for nanoGRPO
Users that are interested in nanoGRPO are comparing it to the libraries listed below
Sorting:
- minimal GRPO implementation from scratch☆96Updated 5 months ago
- Minimal hackable GRPO implementation☆281Updated 6 months ago
- A simplified implementation for experimenting with RLVR on GSM8K, This repository provides a starting point for exploring reasoning.☆121Updated 6 months ago
- ☆120Updated 6 months ago
- Chain of Experts (CoE) enables communication between experts within Mixture-of-Experts (MoE) models☆220Updated 2 months ago
- ☆115Updated 7 months ago
- Implementation of 🥥 Coconut, Chain of Continuous Thought, in Pytorch☆179Updated 2 months ago
- Code for the paper: "Learning to Reason without External Rewards"☆347Updated last month
- Tina: Tiny Reasoning Models via LoRA☆275Updated last week
- A framework to study AI models in Reasoning, Alignment, and use of Memory (RAM).☆277Updated this week
- ☆66Updated last year
- NeurIPS 2024 tutorial on LLM Inference☆47Updated 8 months ago
- Memory layers use a trainable key-value lookup mechanism to add extra parameters to a model without increasing FLOPs. Conceptually, spars…☆344Updated 8 months ago
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.☆173Updated 7 months ago
- Official repo of paper LM2☆41Updated 6 months ago
- [ACL 2025] Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems☆101Updated 2 months ago
- ☆150Updated 9 months ago
- RL significantly the reasoning capability of Qwen2.5-1.5B-Instruct☆30Updated 6 months ago
- A brief and partial summary of RLHF algorithms.☆132Updated 5 months ago
- Exploring Applications of GRPO☆246Updated last month
- ☆89Updated 2 months ago
- RL Scaling and Test-Time Scaling (ICML'25)☆111Updated 7 months ago
- Official repo for paper: "Reinforcement Learning for Reasoning in Small LLMs: What Works and What Doesn't"☆254Updated 3 months ago
- Implementation of the Quiet-STAR paper (https://arxiv.org/pdf/2403.09629.pdf)☆54Updated last year
- Code for "Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate" [COLM 2025]☆170Updated last month
- Code and Configs for Asynchronous RLHF: Faster and More Efficient RL for Language Models☆61Updated 4 months ago
- ☆100Updated last year
- An extension of the nanoGPT repository for training small MOE models.☆178Updated 5 months ago
- A Qwen .5B reasoning model trained on OpenR1-Math-220k☆14Updated 6 months ago
- ☆75Updated 2 months ago